INDEX

Explanations

instances related to various forms of service or operational activities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

usto

-0.19

WithMany

-0.17

opia

-0.15

obl

-0.15

oundation

-0.14

gon

-0.14

sharp

-0.14

ç½

-0.14

ongyang

-0.13

 mutil

-0.13

POSITIVE LOGITS

iosk

0.15

borne

0.15

-mode

0.14

otch

0.14

ccb

0.14

 Dale

0.14

bor

0.13

 rocking

0.13

hood

0.13

.getResponse

0.13

Activations Density 0.379%

instances related to various forms of service or operational activities

No Comments

No Known Activations